Class project entrepreneurship course on starting a business and pitching to Venture Capitalists
Class Duration: 3 months
Tools Used: InVision, Adobe After Effects, Adobe Premiere, Sketch, Illustrator, Keynote, Google Slides, Instapage
Primary Deliverable: A slide deck pitch, executive summary and financial outline
Designer: Eliza Newman-Saul / Business: Lauren Kainski, Tanay Chaturvedi, Seth Bergeson (MBA Candidates, Foster School for Business) / Engineering: Carlo del Mundo (Xnor.ai), Kiron Lebeck (Phd Candidate Allen School), Rosa Thomas (AWS), Max Smiley (Microsoft) Arthur Liang, Ben Ihrig
InstaUP using AI technology to boost engagement by automatically selecting the most engaging photo, editing and cropping the image, suggesting hashtags, and automatically posting it at the most impactful time.
With recent changes to Instagram’s algorithm, which prioritizes posts based on past engagement, organic reach has decreased significantly. Only an estimated 10% of audiences see content. In this new environment, both influencers and marketers need more tools to increase their engagement. How might we create better tools for influencers and aspiring influencers to optimize engagement?
Understanding the User: Who is an Influencer?
An influencer is usually defined as over 2K to 10K followers and earns on average $180 per post
/ Average influencer engagement rate is 5.3% vs. 1.7% overall
/ $1.6B market by 2018
/ Influencer posts doubled from 2016 to 2017 to 1.5M+
Finding Influencers & Signal
We targeted micro-influencers and brands on Instagram in three verticals:
Beauty, Food and Fashion
We created an instagram crawler that generated 1,105 contacts in the Beauty Influencer
/ Market and targeted a number of these contacts directly
/ Through personal contacts found several influencers within our network to interviews
/ Using Instapage and target Facebook ad to create a landing page to target our customer segment
/ Scraped and targeted 200 Instagram Influencers from Faceboo
Audience: 13-19, Female & Male
Platform#2: Facebook Desktop
Audience: 13-19, Female & Male
Platform#3: Facebook, Instagram Audience (Scraped and targeted 200 Influencers)
Drove 60 Clicks to the InstaUp website for an average Cost per Click of $ 0.34
To understand the marketplace we looked at a broad range of products.
Instagram has 800M users and ad spend will increase by 88% this year to $6.9B. Seventy percent of businesses (15M) use Instagram in their marketing efforts. Ad spend on influencers will increase by 50% this year to $2.4B by 2019.
We reviewed 74 products. Competitors provide similar tools as InstaUP but none of them analyze the 80M photos posted on Instagram per day or integrate the four functions InstaUP provides. Competitors fall into three categories: social media management, analytics tools, and targeted solutions. Many freemium photo editing apps exist, and influencers and marketers often use several of these apps in conjunction with scheduling or analytics apps. InstaUP integrates these core functionalities into one intuitive app while also leveraging the billions of photos on Instagram to refine its algorithm.
85% measure success from likes/follows and 46% from comments
50%+ spend 30 mins to 3 hours per post
54% want to be full-time influencers but aren’t yet
Conducted 21 Semi-Structured Interviews
We spoke to Instagram Users who had between 2,000 to 208,000 followers as well expert interviews with the the former Marketing Manager of OfferUp and Co-founder of TBH (which was sold to Facebook in 2017).
"You're selling the idea that machine learning can provide more value, augmenting their photo selection process. But actually, it's the _belief_ of the outcome that attracts people, users don't care how it's done under the hood."
CoFounder of TBH
"I would have loved a tool that could accelerate my Instagram and Facebook acquisition marketing to save us both money and time. I had to manually search through 1,000s of photos to find creative and we were spending a lot of ad money along the way."
Former OfferUp Marketing Manager
Influencers want to create unique, authentic content that doesn't feel repetitive.
“The hardest part is definitely generating new and exciting content. There's SO much out there now and a lot of it is repetitive. I can only look at so many photos of Glossier You before I just get sick of it and don't even want to think about the scent. I know my page is probably more saturated than your average beauty enthusiast who follow beauty accounts, their friends, their favorite restaurant, etc. But it gets hard, and it makes it hard to set yourself apart."
Content creation was time intensive and many influencers wanted to spend more time engaging directly with followers or managing administrative tasks, especially with cross platform demands.
"Aside from testing, writing the blogpost it takes around three hours, on top of that comes about one hour of picture taking and editing and another hour for scheduling promotional tweets/Instagram/Google+ etc., In total between 4-5 hours. Videos take around six hours, accompanying blog post included."
Algorithm changes at Instagram cause a lot of unrest and confusion. Influencers are not clear why some posts do better than others.
"When it comes to optimizing engagement through Instagram, there are so many more challenges now. As an artist it has been so challenging to release content that is not getting recognized due to the new update"
InstaUP’s algorithm uses convolutional neural networks (CNNs), a popular computer vision technique, for image selection. To evaluate the technical feasibility of CNNs on the influencer space, InstaUp's first CNN model focuses on self-portraits ("selfies") since well-curated datasets for selfies already exist. InstaUP's CNN is trained on 46,836 selfies. An image is scored from 0-100% with scores closer to 100% suggesting higher engagement.
CNNs provide a data-driven foundation for inferring "how" engaging an image will be, but CNNs do not adequately describe "why" an image will be engaging. To close this loop, InstaUP uses Google's Cloud Vision API to further analyze image content based on smile, eye contact, clarity, position, empathy, posture, and movement.
Training the Model
I worked with the engineers to look over the photos selected by the model. I noticed that the algorithm seemed to only select smiling photos which seemed antithetical to the goals of many instagram followers. We retrained the model so it was not as biased towards smiles. I suggested that as the product developed we would to scape actual Instagram images so the photos would be more inline with the users goals on the platform.
The group was committed to using Machine Learning, but had no other clear ideas about the design of the product. We considered a very lean product with a quick to market strategy as well as a more robust design with a number of features. We decided to add a few existing core features to the machine learning to automate the whole Instagram posting process. Auto-scheduling and hashtag optimization are existing features in a few available products and the engineers felt they would be able to recreate these features with a little bit of time. Our key insight was users expressed fatigue managing a range of apps.
We created a product with three core features
the most impactful photograph with custom filters and auto-filters based on the Machine Learning
offers a list of popular hashtags currently trending on Instagram
recommends the perfect time to initiate your post
Core functions of InstaUP
I really enjoyed working with a cross-disciplinary team who brought a range of ideas and skills to the project. The larger team provided some scheduling challenges and demanded increased efficiency which will be helpful for future work meetings. It was exciting to learn about edge computing and design for an algorithm that was mostly functioning. Pitching to Venture Capitalists changed my thinking about risk and reward within startups. I had previously assumed a good idea was sufficient but the class showed the importance of scale, to market plan and strong thoughtful leadership as well as compelling design. I learned a number of useful business tools to add to my design thinking.
This proved not as effective as hoped and we decided to create an additional Facebook crawler to generate more targeted Facebook ads to 181 specific influencers in our targeted verticalPlatform#1: Facebook Mobile